What is measuring-ai-proficiency CLAUDE.md?

Instructions for measuring-ai-proficiency, a project that assesses how well a code repository prepares instructions and context for AI coding tools. They define planning, delegation, and a process for recording lessons from mistakes.

Planning multi-step changes, assigning focused work to subagents, and recording project lessons in instruction or learning files.

They provide a repeatable way to handle larger tasks and preserve improvements after corrections. This helps avoid unplanned architectural work and repeated errors.

How pskoett/measuring-ai-proficiency configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to pskoett/measuring-ai-proficiency. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/pskoett/measuring-ai-proficiency/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/pskoett/measuring-ai-proficiency

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/pskoett/measuring-ai-proficiency/claude-md/github.svg)](https://agentmods.dev/instructions/pskoett/measuring-ai-proficiency/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/pskoett/measuring-ai-proficiency/claude-md"><img src="https://agentmods.dev/badge/instructions/pskoett/measuring-ai-proficiency/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/pskoett/measuring-ai-proficiency/claude-md"><img src="https://agentmods.dev/badge/instructions/pskoett/measuring-ai-proficiency/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 4,005 This file is loaded in full into every session.

When invoked 4,005 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.04005	$0.04005
Opus 5.5	$0.01602	$0.01602
Sonnet 5.5	$0.00801	$0.00801
Haiku 4.5	$0.00400	$0.00400

Measured 2mo ago against content hash d263c3116920, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

measuring-ai-proficiency CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 321 lines

How it starts

The opening of the file, as written. The whole thing — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions

Workflow Orchestration

1. Plan Mode Default

Enter plan mode for ANY non-trivial task (3+ steps or architectural decisions)
If something goes sideways, STOP and re-plan immediately - don't keep pushing
Use plan mode for verification steps, not just building
Write detailed specs upfront to reduce ambiguity

2. Subagent Strategy

Use subagents liberally to keep main context window clean
Offload research, exploration, and parallel analysis to subagents
For complex problems, throw more compute at it via subagents
One task per subagent for focused execution

3. Self-Improvement Loop

After ANY correction from the user: use /self-improvement to log:
Write rules for yourself that prevent the same mistake
Ruthlessly iterate on these lessons until mistake rate drops
Review lessons at session start for relevant project

Self-Improvement Workflow

When errors or corrections occur:

Log to .learnings/ERRORS.md, LEARNINGS.md, or FEATURE_REQUESTS.md
Review and promote broadly applicable learnings to:
- CLAUDE.md - project facts and conventions
- AGENTS.md - workflows and automation
- .github/copilot-instructions.md - Copilot context
If the user requests a commit cadence (for example, "commit after each iteration"), create a commit at the end of each completed iteration before asking for the next test.

4. Verification Before Done

Never mark a task complete without proving it works
Diff behavior between main and your changes when relevant
Ask yourself: "Would a staff engineer approve this?"
Run tests, check logs, demonstrate correctness

5. Demand Elegance (Balanced)

For non-trivial changes: pause and ask "is there a more elegant way?"
If a fix feels hacky: "Knowing everything I know now, implement the elegant solution"
Skip this for simple, obvious fixes - don't over-engineer
Challenge your own work before presenting it

6. Autonomous Bug Fixing

When given a bug report: just fix it. Don't ask for hand-holding
Point at logs, errors, failing tests - then resolve them
Zero context switching required from the user
Go fix failing CI tests without being told how

Read the full file on GitHub · 321 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 321 lines · 4,005 tokens per session scan A d263c3116920

Subscribe to this mod's changes

measuring-ai-proficiency CLAUDE.md is an instructions file published in the GitHub repository pskoett/measuring-ai-proficiency (13 stars, last pushed 3mo ago), licensed MIT. It adds 4,005 tokens to every session, about $0.0160 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

measuring-ai-proficiency CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
measuring-ai-proficiency CLAUDE.mdpskoett/measuring-ai-proficiency	Instructions file	13	3mo ago	MIT	A	4,005	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

measuring-ai-proficiency: Instructions file for Claude Code